© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4748
    Prev
    Next
    INDEX
    Explanations

    the word "body" sometimes near the word "school"

    oai_token-act-pair · gemini-2.0-flash

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     body
    -1.81
    body
    -1.31
    Body
    -1.20
     Body
    -1.07
     BODY
    -0.90
     pleaſure
    -0.84
    BODY
    -0.82
     cuerpo
    -0.82
     lichaam
    -0.81
     houſe
    -0.79
    POSITIVE LOGITS
    )}>
    0.80
    contentLoaded
    0.73
    '])->
    0.72
    ()]);
    0.71
    ])))
    0.71
    }');
    0.71
    TypedDataSet
    0.70
    })]
    0.68
    ')}}">
    0.68
    ]}>
    0.66
    Activations Density 1.290%

    No Known Activations